Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Creative & media
Use when the user requests writing, editing, rewriting, final polishing, style review, or structurally faithful translation in a specific author's Chinese style, especially when emphasizing substantial paragraphs, long sentence chains, facts first, sharp judgments, erudite commentary, or reducing meaningless decorative adverbials and complements.
Shopee Media upload module (in the same series as linkfox-shopee-store-auth), forwarding all 6 endpoints in the Shopee Open API Media module via /shopee/developerProxy: upload_image, init_video_upload, upload_video_part, complete_video_upload, get_video_upload_result, and cancel_video_upload. The path is api/v2/media/... (module=130). Trigger when the user mentions Shopee media upload, v2.media.upload_image, or uploading images through the media module. The endpoint names match those in media_space (module=91), but the paths differ; select according to the gateway allowlist.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
Scan or clean prose for AI-generated residue, including unsupported connective tissue, epistemic inflation, over-completed arguments, performed voice, formulaic structure, empty figurative language, stock phrasing, corporate abstraction, hedging, and false enthusiasm. Use for AI-smell cleanup, humanizing model-assisted prose, source-faithful drafting validation, writing polish, or pre-publication checks; enforce silently when composed into drafting or line editing.
Composite any two HTML screens into a locked photo plate of hands holding an open foldable phone — a 1448×1086 still with two blank 495×849 / 498×849 screen slots (left and right) — to make side-by-side meme and comparison videos: TikTok vs Reels, ChatGPT vs Claude, "me vs my friend", before/after, two apps racing. Trigger on: "foldable phone meme", "put X on the left screen and Y on the right", "two-screen comparison video", "the dual-screen phone meme", or any request that names two apps/feeds/chats to show at once. The plate, geometry, and camera are finished — the agent only authors what plays INSIDE the two screens and renders.
Eva Create 2.5.0 content creation entry point. Handles two independent tracks: short videos, spoken scripts, video titles/openings/body; and new writing, continuation, and editing of nonfiction creator articles, WeChat Official Account articles, and opinion essays. When users explicitly want to generate customer inquiries through short videos, build purchase trust in a product, or prompt prospective customers to act, load the Eva trust-building customer acquisition overlay as needed, without creating a second creation workflow. Does not handle Moments posts, Weibo, Xiaohongshu short-form posts, fiction, academic papers, or professional documents. Triggers: /eva-create, /eva-shortvideo, /eva-title, /eva-script, make a short video, improve a video opening, write a complete video script, review short-video pacing, why a short-video script feels weak/where it lacks momentum, write a WeChat Official Account article, turn ideas or materials into an article.
Reescreve textos em português brasileiro para soarem mais humanos e naturais, reduzindo padrões típicos de escrita gerada por IA sem alterar fatos, argumento ou intenção. Use quando o texto em PT-BR parecer genérico, burocrático ou gerado por IA, ou quando o usuário pedir para "humanizar", "dar vida", "tirar cara de IA", "remover AI slop" ou "reescrever com voz". Use também para ESCREVER DO ZERO em português qualquer texto que uma pessoa vai assinar ou publicar (post, artigo, e-mail, proposta, release, README, bio, descrição de produto): nesse caso a lista de padrões funciona como filtro de saída. Para textos em inglês, use a skill-irmã `human-ai`. Também trabalha a partir de notas e transcrições do autor e faz perguntas pontuais quando faltam dados essenciais.
Single-image generation skill for posters, key art, and editorial illustrations. Defaults to gpt-image-2 but is provider-agnostic — the same workflow drives Flux, Imagen, or Midjourney via the active upstream tooling. Output is one or more PNG/JPEG files saved to the project folder.
Generate AI music with Producer via AceDataCloud API. Use when creating songs, generating lyrics, extending tracks, creating covers, swapping vocals/instrumentals, replacing song sections, or uploading reference audio. Supports custom lyrics, instrumental-only mode, and multiple creative actions.
Interactive longform-to-shortform video creator. Extracts viral-ready short clips from long videos using Claude as the orchestrator. Transcribes with faster-whisper (GPU), Claude scores and presents candidate segments interactively, user picks and adjusts, Remotion renders premium animated captions (Bold/Bounce/Clean styles), FFmpeg exports platform-optimized files (YouTube Shorts, TikTok, Instagram Reels). Use when user says "shorts", "short clips", "shortform", "extract clips", "tiktok from video", "reels from video", "vertical clips", or "create shorts".
Generate, revise, translate, and manage App Store / Google Play marketing screenshots. Full flow: initialize a .shots workspace, scrape App Store metadata, research the product from the repo and listing, identify theme, colors, audience, and competitor space, save a strategy brief, craft benefit-driven headlines, and generate 3-up GPT-Image 2 composites via OpenAI direct or fal.ai before cropping them into upload-ready panels. Supports iPhone, iPad, and Android Phone platforms. Triggers: "app store screenshots", "marketing screenshots", "store listing images", "screenshot generation", "app store assets", "google play screenshots", "shots", ".shots", "revise shots", "change screenshots", "fix panels", "redo screenshots", "translate screenshots", "localize", "scrape app store", "fetch metadata", "import app store". Do NOT use for general image generation, social media graphics, or non-store marketing assets.
Direct cinematic shots and coverage for AI-assisted content production. Use when an agent must translate story intent into framing, shot size, lens and perspective, camera position, movement, blocking, screen direction, lighting-aware coverage, continuity, shot specifications, or diagnose why generated or filmed shots do not cut together.
Eva Think 2.5.0 standalone entry point for thought partnering and diagnostics. Use for talking things through, organizing thoughts, untangling dilemmas, clarifying concepts, sorting content questions, calibrating the audience as needed during thinking or creative translation, using samples to support current thinking, checking ordinary text for AI-like qualities, light brainstorming, and saving, retrieving, reviewing, or backing up Eva data; extracting writing style, collecting persona materials, collecting facts about products and services, and diagnosing communication readiness. Also use to clarify confused customer-acquisition goals, fill in decisive business information, or plan a trust-building customer-acquisition content matrix. Hand independent benchmarking, analysis, and learning, as well as critique and explanation of the user's own drafts, to Eva Teaching. Do not take over explicit account/niche positioning, account-positioning reviews, the three homepage elements organized around positioning, coding, finance, file handling, fully specified customer-acquisition copy, or other specialized execution tasks. Triggers: /eva-think, /eva-reframe, /eva-memory, /eva-persona-memory, /eva-product-service, /eva-user-voice, /eva-ai-check, help me think, talk it through with me, my mind is a mess, help me look at this topic, AI-tone check, save this idea, retrieve idea cards, review Eva's memory bank, count memory cards/idea cards/persona cards/product and service cards/style cards, export Eva data, back up all Eva memory cards, package Eva data to the desktop, extract the tone of my social posts, my persona doesn't feel convincing, help me collect product and service information, organize what services I can offer, remember that I'll mainly provide this kind of consulting, broaden the audience or target client inquiries, unclear customer-acquisition goal, customer-acquisition product is unclear, plan a customer-acquisition content matrix. Only disambiguate bare requests such as "build a personal brand", "create a persona", or "build an IP" when /eva or /eva-persona-memory is explicitly invoked, Eva persona-material collection is named, the compatible phrase "persona collection" is used, or the current context is already Eva persona-material work; if the user explicitly chooses account positioning, hand off to eva-positioning. Collect product and service information only when the user explicitly wants to organize, remember, or reuse their own actual offerings; ordinary product analysis, third-party materials, customer service, contracts, CRM, and bare mentions of "product/service/consulting" do not trigger it. Do not take over ordinary file compression, routine project backups, or non-Eva data exports. When the user explicitly requests disciplinary brainstorming from a general entry point, Eva Lens handles it; if already in a Think conversation, shared disciplinary-brainstorming source material may be read as needed, then return to Think. When the user explicitly names the topic-audience finder or asks directly "what audience is behind this, who does it resonate with, who is it for?", the eva-audience-finder is the primary entry point.
Turn talking-head footage into a finished reel, YouTube Short, or short advertisement with curiosity-led openings, earned payoffs, story-driven cuts, transcript-synced motion graphics, moving B-roll, captions, subtle music, and synchronized sound effects. Use for short-form editing; use edit-video for long-form videos and cut-silences for pause removal alone.
Dialogue writing and revision for screen and stage (对白/台词/潜台词) — merged from Robert McKee's Dialogue (dialogue as action, said/unsaid/unsayable, exposition as ammunition, beat = action/reaction gerunds, flaws of credibility/language/content/design, character-specific vocabulary and grammar, seven scene analyses), Richard Walter (economy, subtext, argument, no small talk, no parentheticals, silence), Neill Hicks (listening, on-the-nose exceptions, energy, five-step exercise), Lu Jun (语言要美; 典雅美/通俗美, 对话三要求 动作性/性格化/潜台词), Lajos Egri (dialogue born of three-dimensional character, escalation), Blake Snyder (cover-the-names test), and screwball-comedy dialogue conventions. Use when writing or polishing dialogue, fixing on-the-nose or expository lines, giving each character a distinct voice, converting a two-hander into a trialogue, writing comedy exchanges, or cutting speeches. Chinese-opera lyrics (戏曲唱词) are in sw-chinese-opera-banqiang, not here.
Maximum control over AI image generation—write structured VGL (Visual Generation Language) JSON that explicitly controls every visual attribute. Define exact object placement, lighting direction, camera angle, lens focal length, composition, color scheme, and artistic style as deterministic JSON instead of ambiguous natural language. Use this skill when you need reproducible image generation, precise control over scene composition, or want to convert a natural language image request into a structured JSON schema for Bria Fibo models. Triggers on requests for structured prompts, controllable generation, VGL JSON, deterministic image descriptions, or Bria/FIBO structured_prompt format
Install, configure, and start FireRed-OpenStoryline from source on a local machine. Use when a user asks to set up OpenStoryline, troubleshoot installation, download required resources, fill config.toml API keys, or launch the MCP and web services, as well as Chinese requests like “安装 OpenStoryline”, “配置 OpenStoryline”, “启动 OpenStoryline”, “把 OpenStoryline 跑起来”, “修复 OpenStoryline 安装问题”, or “排查 OpenStoryline 启动失败”.
Reviews lyrics and prose for AI-written patterns (abstract noun stacking, over-explained metaphors, cliche escalation, missing idiosyncrasy, prose AI tells). Advisory Warning/Info severity — flags issues, does not block or rewrite. Use when reviewing lyrics for authenticity or before generation to catch AI-sounding language
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
Write correct Sarvam Bulbul TTS code — bulbul:v4-flash persona speaker IDs (voice_language_style), REST, HTTP stream, WebSocket, pronunciation dictionaries, and v3/v4 traps (short names rejected on v4, param ranges). Use this skill when generating speech in an app with Python or JS/TS. For live TTS in chat via MCP, use sarvam-mcp instead.
Create visually consistent storyboards using PJ Ace's 2x2 Grid Shots technique, keeping lighting, characters, and settings uniform across shots. Use when: **After finalizing a video script** - Turn the concept into visuals; **When visual consistency is needed** - Keep characters and lighting consistent across shots; **Preparing assets for animation** - Frames ready for Veo, Runway, Kling; **Presenting a storyboard to a client** - Visualize before production;...
Measure writing-style statistics (sentence length, vocabulary, transitions, phrasing) from 5 to 10 posts you or your client wrote, and produce a voice profile for VOICE.md, blog-persona, and blog-write. Use for "learn my style", "build a writing baseline". It describes style; it does not detect or attribute authorship, and it is not for scoring a post (blog-analyze) or writing brand rules (blog-brand).
Create new genre documentation files for the bitwize-music genre library. Use when the user wants to add a genre, says “/genre-creator”, “neues Genre erstellen”, “Genre hinzufuegen”, “add genre”, or asks to create genre documentation. Takes a genre name as an argument.
Build a complete audio identity for your brand using a 7-step methodology—from brand assessment through deployment—creating memorable sonic assets that drive recognition and trust. Use when creating audio branding for a new company, refreshing outdated brand sounds, developing audio guidelines for consistent usage, planning sonic identity across touchpoints, or briefing agencies on audio branding projects.
Creates and retrieves AI video and image-related assets via the Arcads external API (Seedance 2.0, Sora 2, Veo 3.1, Kling, Grok Video, Nano Banana, b-roll, scene, script/actor flows). Loads prompts from the bundled prompting guide and model library, respects HTTP Basic auth from ARCADS_API_KEY, and polls assets/videos until ready. Use when the user mentions Arcads, external-api.arcads.ai, Seedance, Sora2, Veo, Kling, Nano Banana, b-roll, UGC scripts, or generating marketing creative through Arcads.
Analyze and transform faces via AceDataCloud API. Use when detecting face keypoints, beautifying portraits, aging/de-aging faces, swapping genders, replacing faces between photos, creating cartoon avatars, or detecting liveness. Provides 7 specialized face APIs.
Turn one line (“a turbofan jet engine”, “a mechanical watch”, “an LVAD heart pump”) into a photorealistic, physics-based, interactive 3D simulation of that machine in a single HTML file, plus a 20- to 30-second film to post. Use real proportions in metres, real materials (PBR metals, paints, polymers, glass), studio lighting with soft shadows, and moving parts driven by a small solver computing real numbers (thrust, torque, rpm, flow, pressure, efficiency). Include modes to explode it, cut it open with clean section caps, x-ray it, slow it down, label it, and break it. Use whenever someone asks to build, simulate, visualize, explain, or “show how X works” for any machine, engine, mechanism, device, instrument, or hardware; wants an interactive 3D model or cutaway; or wants a video of a machine for a post, even if they never say “simulation” or “three.js”.
Use when an agent is asked to draft, rewrite, edit, review, polish, copyedit, simplify, humanize, or create written prose, including creative writing, essays, posts, scripts, speeches, emails, documentation, product copy, and other style-sensitive text. Apply George Orwell's six rules and ASD-STE100 Simplified Technical English as a plain-English discipline while preserving the user's intended meaning, audience, tone, and explicit constraints
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.